Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3873 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.7105. Min Act: -0.0000

Data Index: 323014 (The Pile)

Max Activating Token Index: 533

Text #1

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.4663. Min Act: -0.0000

Data Index: 851367 (The Pile)

Max Activating Token Index: 547

Text #2

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.4328. Min Act: -0.0000

Data Index: 1981716 (The Pile)

Max Activating Token Index: 296

Text #3

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.3670. Min Act: -0.0000

Data Index: 350798 (The Pile)

Max Activating Token Index: 603

Text #4

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.3898. Min Act: -0.0000

Data Index: 402676 (The Pile)

Max Activating Token Index: 118

Text #5

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.3711. Min Act: -0.0000

Data Index: 1099388 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.3733. Min Act: -0.0000

Data Index: 145751 (The Pile)

Max Activating Token Index: 44

Text #7

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.3526. Min Act: -0.0000

Data Index: 1181616 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.3389. Min Act: -0.0000

Data Index: 871194 (The Pile)

Max Activating Token Index: 958

Text #9

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.3415. Min Act: -0.0000

Data Index: 1005960 (The Pile)

Max Activating Token Index: 788

Text #10

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1267172 (The Pile)

Max Activating Token Index: 358

Text #11

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.3300. Min Act: -0.0000

Data Index: 1947828 (The Pile)

Max Activating Token Index: 375

Text #12

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.3054. Min Act: -0.0000

Data Index: 473120 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.3201. Min Act: -0.0000

Data Index: 1815983 (The Pile)

Max Activating Token Index: 36

Text #14

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.2858. Min Act: -0.0000

Data Index: 1198982 (The Pile)

Max Activating Token Index: 83

Text #15

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.2990. Min Act: -0.0000

Data Index: 778069 (The Pile)

Max Activating Token Index: 29

Text #16

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.3063. Min Act: -0.0000

Data Index: 1628688 (The Pile)

Max Activating Token Index: 825

Text #17

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1129794 (The Pile)

Max Activating Token Index: 432

Text #18

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.2858. Min Act: -0.0000

Data Index: 538690 (The Pile)

Max Activating Token Index: 656

Text #19

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.3013. Min Act: -0.0000

Data Index: 1961069 (The Pile)

Max Activating Token Index: 287